检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zheng, Yaozong Zhong, Bineng Liang, Qihua Li, Guorong Ji, Rongrong Li, Xianxian The Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China The Guangxi Key Laboratory of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China The School of Computer Science and Technology Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Media Analytics and Computing Lab Department of Artificial Intelligence School of Informatics Xiamen University 361005 China

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOText and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Discrepancy and Thematic Bibliometric Analyses of the Remaining Limitations in Artificial Intelligence

Discrepancy and Thematic Bibliometric Analyses of the Remain...

引用

Computing (ICOCO), IEEE International Conference on

作者： Mahayaudin M. Mansor Nurain Ibrahim Noor Fadhilah Ahmad Radi Nadirah Abdul Rahim Syarul Heiry Yahaya Mohd Aftar Abu Bakar Roslinazairimah Zakaria School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Malaysia Institute of Big Data Analytics and Artificial Intelligence Universiti Teknologi MARA Malaysia Department of Electrical and Computer Engineering Kuliyyah of Engineering International Islamic University Malaysia Department of Science Computer and Mathematics Universiti Teknologi MARA (Penang Campus) Malaysia Department of Mathematical Sciences Faculty of Science & Technology Universiti Kebangsaan Malaysia Centre for Mathematical Sciences Universiti Malaysia Pahang Al-Sultan Abdullah Malaysia

ISBN: (数字)9798331530303

ISBN: (纸本)9798331530310

As artificial intelligence (AI) advances, it is essential to continuously comprehend its limitations to optimise the integration of AI into autonomous systems that empower humans. The first objective of this study is to highlight the key capabilities of both humans and AI, focusing on the differences and identifying limitations of AI from the literature. Through discrepancy analysis, this study uses a Venn diagram to visualise the remaining limitations of AI into five key domains: (i) emotional intelligence, (ii) consciousness and awareness, (iii) creative imagination, (iv) communication, and (v) ethical decision-making. Furthermore, this study employs thematic bibliometric analysis to provide a more detailed examination of each AI limitation as the second objective. This study has identified underdeveloped and emerging research themes with potential for future development, such as emotion recognition, human-computer interaction, digital health, and situational awareness, which may require further research. Additionally, this study commends the ongoing efforts to harness AI’s computational power and algorithmic innovations to enhance AI’s overall performance and applicability.

关键词： Visualization Technological innovation Ethics Emotion recognition Bibliometrics Decision making Focusing Electronic healthcare Object recognition Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Large Language Models for Sexual, Reproductive, and Maternal Health Rights*

Large Language Models for Sexual, Reproductive, and Maternal...

引用

IEEE International Conference on Healthcare informatics (ICHI)

作者： Walelign Sewunetie Assefa Beza Hailemariam Abebe Tesfamariam M Abuhay Wasyihun Admass Hayat Hassen Tsion Haile Hana Hailemariam Lydia Debebe Nurlign Moges Nathnael Bekele Surafel L Tilahun Mahlet Berta Mahlet Mammo Seid Muhie Yimam Kovacs Laszlo School of Computing Debre Markos University Ethiopia Faculty of Computing Bahir Dar University Ethiopia University of Gondar Ethiopia Queen's University Canada School of Computing Mekdela Amba University Mekdela Ethiopia College of Medicine and Health Sciences University of Gondar Ethiopia Saint Paul's Hospital Millennium Medical College AA Ethiopia College of Medicine and Health Sciences Bahir Dar University Ethiopia College of Medicine and Health Sciences Debre Markos University Ethiopia Addis Ababa Science and Technology University Ethiopia HPC & Big Data Analytics CoE Addis Ababa Science and Technology University Ethiopia House of Computing and Data Science University of Hamburg Hamburg Germany Institute of Informatics Univerisity of Miskolc Miskolc Hungary

ISBN: (数字)9798350383737

ISBN: (纸本)9798350383744

This research explores the potential of Large Language Models in the context of healthcare solutions, with a specific focus on Sexual, Reproduc-tive, and Maternal Health Rights (SRMHR) Question Answering (QA) in the low-resource language, Amharic (““'Ie;;:). To construct the dataset, we first collected data from medical textbooks and guidelines authored by reputable medical institutions and organizations. U ti-lizing automatic question-and-answer generation techniques, we then generated pairs for the dataset. Sub-sequently, the dataset underwent annotation, translation, and evaluation processes, resulting in a refined collection of 2.8k Amharic datasets. We use the dataset to fine-tune the LLaMA-2-Amharic model, with test results assessed using BLEU scores and human-level evaluations, demonstrating promising outcomes. The curated Amharic SRMHRQA dataset serves as a foun- dational resource for future research. However, further enhancements are necessary to optimize its efficacy, particularly within the realm of SRMHR for low- resource languages like Amharic. Future research could involve scaling up the dataset in terms of size, quality, and domain coverage.

关键词： Annotations Large language models Medical services Organizations Question answering (information retrieval) informatics Guidelines

来源：评论

学校读者我要写书评

暂无评论

Annual workers’ income prediction using data mining techniques

引用

AIP Conference Proceedings 2024年第1期3123卷

作者： Muhammad Syawalludin Yahaya Mohammad Hafshah Hasbullah Siti Afiqah Muhamad Jamil Ahmad Zia Ul–Saufie Nurain Ibrahim School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA 40450 Shah Alam Selangor Malaysia Institute for Big Data Analytics and Artificial Intelligence (IBDAAI) Kompleks Al-Khawarizmi Universiti Teknologi MARA 40450 Shah Alam Selangor Malaysia

Predicting annual workers income requires ones to deep dive into several factors. Factors that majorly being discuss were age, gender, education and occupation. On the other hand, there are other factors that may affect the annual workers income where it yet to be discussed. The traditional way of predicting the annual workers income was multiple linear regression. This parametric approach requires assumptions to be fulfilled and this will actions is a time-consuming activity. data mining approach in predicting the workers income is important to understand on how the economy and compensation work in the United States. Machine learning will cover all aspect without needing to fulfil certain assumptions as compared to traditional method. Hence, the best way to predict the worker’s income in the United States is the best using machine learning and concurrently solve the SDG 8: Decent Work & Economic Growth aspect. The dataset used in this study is acquired from Kaggle website. At first, features weight using filter method (Weight by Information Gain, Weight by Information gain Ratio and Weight by Chi – Squared Statistics) were taken to identify the influential factors towards annual workers’ income. The three different methods employed in the model to predict worker income are logistic regression, decision trees, and artificial neural networks. The second goal is to contrast the effectiveness of worker income prediction using under sampling and oversampling techniques. The results show that, with the exception of decision tree, oversampling strategy provides the best performance of prediction model when compared to under sampling technique. Since under sampling techniques randomly delete observations when there is a chance that such observations could be significant to the data and have an impact on the prediction model, oversampling techniques perform better than under sampling techniques. The third goal is to identify the most effective classification model for predi

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dynamic Resource Scheduler for Distributed Deep Learning Training in Kubernetes

Dynamic Resource Scheduler for Distributed Deep Learning Tra...

引用

International Conference of Advanced informatics: Concept, Theory and Application (ICAICTA)

作者： Muhammad Fadhriga Bestari Achmad Imam Kistijantoro Anggrahita Bayu Sasmita School of Electrical Engineering and Informatics ITB Indonesia University Center of Excellence on Artificial Intelligence for Vision Natural Language Processing & Big Data Analytics (U-CoE AI-VLB) Indonesia

ISBN: (纸本)9781728180380;9781728180397

Distributed deep learning is a method of machine learning that is used today due to its many advantages. One of the many tools used to train distributed deep learning model is Kubeflow, which runs on top of Kubernetes. Kubernetes is a containerized application orchestrator that ease the deployment process of applications. This in turn makes distributed deep learning training done in Kubeflow easier and manageable. Works on a dynamic resource scheduler in Kubernetes for deep learning training have been done before, such as DRAGON that proposed scheduler with autoscaling and gang scheduling capabilities, and OASIS that proposed a utility system with price function. In this work, we propose to combine DRAGON's and OASIS' approach to make a scheduler with weighted autoscaling capabilities and schedule its jobs with gang scheduling. Some modifications are done on DRAGON's autoscaling function. We try to increase the frequency of scaling up function calls and reduce the frequency of scaling down function to make the training process more efficient. Weights are used to determine the priority of each jobs, where jobs with higher resource requirements are considered more important. Weight of each jobs will influence the autoscaling function of the scheduler. Experiment and evaluation done using a set of Tensorflow jobs results in an increase of training speed by over 26% in comparison with the default Kubernetes scheduler.

关键词： Training Deep learning Schedules Estimation Tools Dynamic scheduling informatics

来源：评论

学校读者我要写书评

暂无评论

Robust Adversarial Example as Captcha Generator

Robust Adversarial Example as Captcha Generator

引用

International Conference of Advanced informatics: Concept, Theory and Application (ICAICTA)

作者： Nicolaus Boby Ardhita Nur Ulfa Maulidevi School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia School of Electrical Engineering and Informatics Institut Teknologi Bandung U-CoE AI-VLB (Artificial Intelligence for Vision Natural Language Processing & Big Data Analytics) Bandung Indonesia

ISBN: (纸本)9781728180380;9781728180397

Adversarial example as one of the weaknesses of Deep Learning, can be used to attack image recognition models. Image recognition model can be used to attack common image CAPTCHA schemes, as the AI algorithm can recognize images to pass the test. So with applying robust adversarial example to image CAPTCHA, we produced a way to synthesize a robust CAPTCHA generator that are robust and cannot be easily attacked by image recognition algorithms.

关键词： Deep learning Image recognition Generators informatics Artificial intelligence CAPTCHAs

来源：评论

学校读者我要写书评

暂无评论

Influence of relative Quality and experience in female single tennis match performance using cluster and discriminant analysis

引用

AIP Conference Proceedings 2024年第1期3123卷

作者： Norhalilah Che Husain Aida Wati Zainan Abidin Kadzim Mohd Rosdi Zan Azma Nasruddin Hafiszah Ismail Big Data Analytics Core Team Department of Statistics Malaysia Presint 1 62514 Putrajaya Malaysia School of Mathematical Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam 40450 Selangor Malaysia Intelligent Data Analytics Competence Centre College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam 40450 Selangor Malaysia Department of Geomatics Sarawak Shell Berhad Miri 98000 Sarawak Malaysia School of Computer Sciences College of Computing Informatics and Mathematics Universiti Teknologi MARA Shah Alam 40450 Selangor Malaysia School of Real Estate and Building Surveying College of Built Environment Universiti Teknologi MARA Shah Alam 40450 Selangor Malaysia

Due to the fast growth of advanced technology, the volume of sports data has increased, which has led to researchers’ interest in studying the tennis data set. Tennis is an example of an individual sport where the opponent's skills and anticipation are just as significant as the player's personal qualities and abilities in determining the outcome of a match. Winning is greatly influenced by the experience as well as the comparative talent of the opponents. Hence, this study has two aims: first, to calculate the Relative Quality of each player and then classify the similar patterns of the female single players’ performance based on their experience and Relative Quality, and second, to determine which weightings of the variables best discriminate between winners and losers for each cluster. The match statistics for four 2018 Grand Slam main-draw women’s singles matches were collected from separate official tournament websites: the Australian Open, the French Open, Wimbledon, and the US Open, which consist of 1016 observations. The methods used in this study are hierarchical-based clustering analysis, which groups the players based on these two attributes, and discriminant analysis, which governs which attributes are best to discriminate among the winners and losers for each of the four clusters. Based on the cluster analysis results, four clusters were identified and designated as LEHRQ, LELRQ, HEHRQ, and HEHRQ. The outcome of the discriminant analysis shows that the performance of a tennis player is most likely reliant on holding their serve and remaining powerful to break their opponent's serve. Moreover, there are variations in the components among clusters. Identifying to which group a player belongs provides valuable assistance to both players and coaches in optimizing their training strategies and augmenting their performance by refining their serving and return abilities.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transparent Tracing System on gRPC based Microservice Applications Running on Kubernetes

Transparent Tracing System on gRPC based Microservice Applic...

引用

International Conference of Advanced informatics: Concept, Theory and Application (ICAICTA)

作者： Abram Perdanaputra Achmad Imam Kistijantoro School of Electrical Engineering and Informatics Institut Teknologi Bandung Bandung Indonesia University Center of Excellence on Artificial Intelligence for Vision Natural Language Processing & Big Data Analytics (U-CoE AI-VLB) Indonesia

ISBN: (纸本)9781728180397

With the increasing use of distributed system-based applications, the demand for tracing system as debugging tools for respective system also increases. Specifically, on Kubernetes environment, tracing on microservice- based systems is not an easy task due to the heterogeneity of the architecture. gRPC provides a more performant way to communicate between microservice. This leads to a need of a tracing system that are transparent with respect to the applications that supports gRPC as its main communication protocol to ease the use of tracing on heterogeneous environment. The approach used to achieve transparency is passive tracing. Passive tracing requires the system to perform tracing without any modifications to the application or the application runtime. This system implements passive tracing by performing packet interception on every packet sent by the application, recording the gRPC request data, and writing the trace data to a log. The resulting log will be stored in Elasticsearch and visualized using Kibana for further analysis. The implementation of this system adds an average overhead CPU usage of 8.8% with Elastic stack and 3.5% without Elastic stack and memory usage of 959 MB with Elastic stack and 378 MB without Elastic stack. In addition, 61.9% of the actual request successfully traced using this system. This implementation successfully traces transparently, but the log-based approach makes the system unable to trace recursively. This results request causality will not be known. This means the trace results can only produce metadata for each request without knowing the relationship of one request with another. Furthermore, the absence of request causality results an inaccurate number of the success rate of the trace due to matching can only be done by service name and method without the context of each request.

关键词： Runtime Protocols data visualization Debugging Writing Tools Metadata

来源：评论

学校读者我要写书评

暂无评论

g-circulant matrix and its matrix-vector multiplication algorithm on transformer neural network

引用

AIP Conference Proceedings 2024年第1期3201卷

作者： Euis Asriani Intan Muchtadi-Alamsyah Ayu Purwarianti Doctoral Program of Mathematics Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Indonesia Algebra Research Group Faculty of Mathematics and Natural Sciences Institut Teknologi Bandung Indonesia University Center of Excellence on Artificial Intelligence for Vision Natural Language Processing and Big Data Analytics (U-CoE AI-VLB) Institut Teknologi Bandung Indonesia Informatics Research Group School of Electrical Engineering and Informatics Institut Teknologi Bandung Indonesia

A g-circulant matrix is an n-dimensional matrix Cn,g that can be expressed as Cn,g=[c(gr−s)modn]r,s=0n−1 . This study will investigate the use of g-circulant matrices as weight matrices on transformer neural networks for machine translation. On transformer model tested, the g-circulant weight matrix undergoes multiplication with any vector and involves the DCT-DST algorithm. This algorithm is proposed as a substitute for the commonly used FFT algorithm. For this reason, an orthogonal matrix Un,g was defined by multiplying the Un matrix and appropriate permutation matrix, where Un matrix is a matrix that is spanned by the combination of the real and imaginary parts of eigenvectors of the real 1-circulant matrix. Then we form a Schur decomposition of the g-circulant matrix, composes the Qn,g matrix, and using the DCT-DST to formulate the multiplication of Qn,gUn,g. We discovered that 2-circulant matrices are outperform compared to the other g-circulant matrices and the original model of transformer in terms of accuracy and loss training.

关键词：

来源：评论

学校读者我要写书评

暂无评论

big data Integration Design for General Election in Indonesia

Big Data Integration Design for General Election in Indonesi...

引用

International Conference on informatics and Computing (ICIC)

作者： Gede Karya Wikan Danar Sunindyo Benhard Sitohang Saiful Akbar Adi Mulyanto School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia Parahyangan Catholic University Bandung Indonesia PUI-PT Artificial Intelligence for Vision Natural Language Processing & Big Data Analytics (AI-VLB) Bandung Institute of Technology Bandung Indonesia

ISBN: (数字)9781728180472

ISBN: (纸本)9781728180489

The use of big-data analysis in elections in Indonesia has been started since the Governor Election of DKI-Jakarta in 2012 until the Presidential Election in 2019. However, its use is limited to using analytical sentiment to map support and predict election results using social-media data. We see that there is a great opportunity to use big data for a broader election, which is to facilitate the fulfillment of the information and analysis needs of all election stakeholders. But the main problem in using big-data is the integration of big data from various sources with a variety of different formats and large volumes, in addition to the issues of analysis and visualization. For this reason, in this paper, we propose a big-data integration design to meet the needs of elections in Indonesia. This big-data integration design was developed based on election regulations in Indonesia, knowledge of big-data, and the use of a NoSQL database to store unstructured data. The election big-data integration design that we propose includes (1) the information needs of each election stakeholder; (2) the potential for big-data in fulfilling the information needs of every election stakeholder; (3) big-data analysis architecture for elections; (4) big-data integration architecture for elections; (5) crawler architecture; and (5) technology architecture that can implement big-data integration design for elections. Currently, the implementation of this design is in progress in the P3MI-ITB research project.

关键词： Voting NoSQL databases Computer architecture big data Regulation Stakeholders informatics

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：